Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder

Authors

  • Meng-Hsuan Yu Peking University
  • Juntao Li Peking University
  • Danyang Liu Shanghai Jiao Tong University
  • Dongyan Zhao Peking University
  • Rui Yan Peking University
  • Bo Tang Southern University of Science and Technology
  • Haisong Zhang Tencent AI Lab

DOI:

https://doi.org/10.1609/aaai.v34i02.5538

Abstract

Automatic Storytelling has consistently been a challenging area in the field of natural language processing. Despite considerable achievements have been made, the gap between automatically generated stories and human-written stories is still significant. Moreover, the limitations of existing automatic storytelling methods are obvious, e.g., the consistency of content, wording diversity. In this paper, we proposed a multi-pass hierarchical conditional variational autoencoder model to overcome the challenges and limitations in existing automatic storytelling models. While the conditional variational autoencoder (CVAE) model has been employed to generate diversified content, the hierarchical structure and multi-pass editing scheme allow the story to create more consistent content. We conduct extensive experiments on the ROCStories Dataset. The results verified the validity and effectiveness of our proposed model and yields substantial improvement over the existing state-of-the-art approaches.

Downloads

Published

2020-04-03

How to Cite

Yu, M.-H., Li, J., Liu, D., Zhao, D., Yan, R., Tang, B., & Zhang, H. (2020). Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder. Proceedings of the AAAI Conference on Artificial Intelligence, 34(02), 1741-1748. https://doi.org/10.1609/aaai.v34i02.5538

Issue

Section

AAAI Technical Track: Game Playing and Interactive Entertainment